Binary classification of copy number alteration profiles in liquid biopsy with potential clinical impact in advanced NSCLC.

Liquid biopsy has recently emerged as an important tool in clinical practice particularly for lung cancer patients. We retrospectively evaluated cell-free DNA analyses performed at our Institution by next generation sequencing methodology detecting the major classes of genetic alterations. Starting from the graphical representation of chromosomal alterations provided by the analysis software, we developed a support vector machine classifier to automatically classify chromosomal profiles as stable (SCP) or unstable (UCP). High concordance was found between our binary classification and tumor fraction evaluation performed using shallow whole genome sequencing. Among clinical features, UCP patients were more likely to have ≥ 3 metastatic sites and liver metastases. Longitudinal assessment of chromosomal profiles in 33 patients with lung cancer receiving immune checkpoint inhibitors (ICIs) showed that only patients that experienced early death or hyperprogressive disease retained or acquired an UCP within 3 weeks from the beginning of ICIs. UCP was not observed following ICIs among patients that experienced progressive disease or clinical benefit. In conclusion, our binary classification, applied to whole copy number alteration profiles, could be useful for clinical risk stratification during systemic treatment for non-small cell lung cancer patients.

Machine learning in onco-pharmacogenomics: a path to precision medicine with many challenges.

Over the past two decades, Next-Generation Sequencing (NGS) has revolutionized the approach to cancer research. Applications of NGS include the identification of tumor specific alterations that can influence tumor pathobiology and also impact diagnosis, prognosis and therapeutic options. Pharmacogenomics (PGx) studies the role of inheritance of individual genetic patterns in drug response and has taken advantage of NGS technology as it provides access to high-throughput data that can, however, be difficult to manage. Machine learning (ML) has recently been used in the life sciences to discover hidden patterns from complex NGS data and to solve various PGx problems. In this review, we provide a comprehensive overview of the NGS approaches that can be employed and the different PGx studies implicating the use of NGS data. We also provide an excursus of the ML algorithms that can exert a role as fundamental strategies in the PGx field to improve personalized medicine in cancer.